--- library_name: pytorch license: apache-2.0 pipeline_tag: object-detection tags: - real_time - android --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mediapipe_face/web-assets/model_demo.png) # MediaPipe-Face-Detection: Optimized for Mobile Deployment ## Detect faces and locate facial features in real-time video and image streams Designed for sub-millisecond processing, this model predicts bounding boxes and pose skeletons (left eye, right eye, nose tip, mouth, left eye tragion, and right eye tragion) of faces in an image. This model is an implementation of MediaPipe-Face-Detection found [here](https://github.com/zmurez/MediaPipePyTorch/). This repository provides scripts to run MediaPipe-Face-Detection on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/mediapipe_face). ### Model Details - **Model Type:** Object detection - **Model Stats:** - Input resolution: 256x256 - Number of parameters (MediaPipeFaceDetector): 135K - Model size (MediaPipeFaceDetector): 565 KB - Number of parameters (MediaPipeFaceLandmarkDetector): 603K - Model size (MediaPipeFaceLandmarkDetector): 2.34 MB - Number of output classes: 6 | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | MediaPipeFaceDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.555 ms | 0 - 6 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.63 ms | 1 - 7 MB | FP16 | NPU | [MediaPipe-Face-Detection.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so) | | MediaPipeFaceDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.038 ms | 0 - 9 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.onnx) | | MediaPipeFaceDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.403 ms | 0 - 22 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.458 ms | 1 - 24 MB | FP16 | NPU | [MediaPipe-Face-Detection.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so) | | MediaPipeFaceDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.75 ms | 1 - 34 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.onnx) | | MediaPipeFaceDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.425 ms | 0 - 20 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.47 ms | 1 - 20 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.721 ms | 1 - 27 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.onnx) | | MediaPipeFaceDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.555 ms | 0 - 6 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.61 ms | 1 - 3 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | SA7255P ADP | SA7255P | TFLITE | 18.736 ms | 0 - 12 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | SA7255P ADP | SA7255P | QNN | 18.973 ms | 1 - 10 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.554 ms | 0 - 6 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.607 ms | 1 - 3 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | SA8295P ADP | SA8295P | TFLITE | 1.153 ms | 0 - 18 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | SA8295P ADP | SA8295P | QNN | 1.402 ms | 0 - 14 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.555 ms | 0 - 6 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.62 ms | 1 - 3 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | SA8775P ADP | SA8775P | TFLITE | 1.244 ms | 0 - 14 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | SA8775P ADP | SA8775P | QNN | 1.431 ms | 1 - 11 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.807 ms | 0 - 24 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) | | MediaPipeFaceDetector | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.902 ms | 1 - 22 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.753 ms | 1 - 1 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.04 ms | 2 - 2 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.onnx) | | MediaPipeFaceLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.194 ms | 0 - 8 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.274 ms | 0 - 10 MB | FP16 | NPU | [MediaPipe-Face-Detection.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so) | | MediaPipeFaceLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.506 ms | 0 - 7 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.onnx) | | MediaPipeFaceLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.139 ms | 0 - 25 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.206 ms | 0 - 18 MB | FP16 | NPU | [MediaPipe-Face-Detection.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so) | | MediaPipeFaceLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.392 ms | 0 - 25 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.onnx) | | MediaPipeFaceLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.168 ms | 0 - 17 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.214 ms | 0 - 17 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.391 ms | 0 - 18 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.onnx) | | MediaPipeFaceLandmarkDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.192 ms | 0 - 8 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.276 ms | 0 - 3 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | SA7255P ADP | SA7255P | TFLITE | 3.551 ms | 0 - 11 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | SA7255P ADP | SA7255P | QNN | 3.835 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.197 ms | 0 - 8 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.274 ms | 0 - 3 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | SA8295P ADP | SA8295P | TFLITE | 0.57 ms | 0 - 16 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | SA8295P ADP | SA8295P | QNN | 0.909 ms | 0 - 14 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.197 ms | 0 - 9 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.28 ms | 0 - 2 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | SA8775P ADP | SA8775P | TFLITE | 0.502 ms | 0 - 10 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | SA8775P ADP | SA8775P | QNN | 0.794 ms | 0 - 10 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.274 ms | 0 - 21 MB | FP16 | NPU | [MediaPipe-Face-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) | | MediaPipeFaceLandmarkDetector | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.41 ms | 0 - 18 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.372 ms | 0 - 0 MB | FP16 | NPU | Use Export Script | | MediaPipeFaceLandmarkDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.539 ms | 3 - 3 MB | FP16 | NPU | [MediaPipe-Face-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.onnx) | ## Installation Install the package via pip: ```bash pip install qai-hub-models ``` ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`. With this API token, you can configure your client to run models on the cloud hosted devices. ```bash qai-hub configure --api_token API_TOKEN ``` Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information. ## Demo off target The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input. ```bash python -m qai_hub_models.models.mediapipe_face.demo ``` The above demo runs a reference implementation of pre-processing, model inference, and post processing. **NOTE**: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above). ``` %run -m qai_hub_models.models.mediapipe_face.demo ``` ### Run model on a cloud-hosted device In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following: * Performance check on-device on a cloud-hosted device * Downloads compiled assets that can be deployed on-device for Android. * Accuracy check between PyTorch and on-device outputs. ```bash python -m qai_hub_models.models.mediapipe_face.export ``` ``` Profiling Results ------------------------------------------------------------ MediaPipeFaceDetector Device : Samsung Galaxy S23 (13) Runtime : TFLITE Estimated inference time (ms) : 0.6 Estimated peak memory usage (MB): [0, 6] Total # Ops : 111 Compute Unit(s) : NPU (111 ops) ------------------------------------------------------------ MediaPipeFaceLandmarkDetector Device : Samsung Galaxy S23 (13) Runtime : TFLITE Estimated inference time (ms) : 0.2 Estimated peak memory usage (MB): [0, 8] Total # Ops : 100 Compute Unit(s) : NPU (100 ops) ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/mediapipe_face/qai_hub_models/models/MediaPipe-Face-Detection/export.py) leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model on-device. Lets go through each step below in detail: Step 1: **Compile model for on-device deployment** To compile a PyTorch model for on-device deployment, we first trace the model in memory using the `jit.trace` and then call the `submit_compile_job` API. ```python import torch import qai_hub as hub from qai_hub_models.models.mediapipe_face import Model # Load the model model = Model.from_pretrained() face_detector_model = model.face_detector face_landmark_detector_model = model.face_landmark_detector # Device device = hub.Device("Samsung Galaxy S23") # Trace model face_detector_input_shape = face_detector_model.get_input_spec() face_detector_sample_inputs = face_detector_model.sample_inputs() traced_face_detector_model = torch.jit.trace(face_detector_model, [torch.tensor(data[0]) for _, data in face_detector_sample_inputs.items()]) # Compile model on a specific device face_detector_compile_job = hub.submit_compile_job( model=traced_face_detector_model , device=device, input_specs=face_detector_model.get_input_spec(), ) # Get target model to run on-device face_detector_target_model = face_detector_compile_job.get_target_model() # Trace model face_landmark_detector_input_shape = face_landmark_detector_model.get_input_spec() face_landmark_detector_sample_inputs = face_landmark_detector_model.sample_inputs() traced_face_landmark_detector_model = torch.jit.trace(face_landmark_detector_model, [torch.tensor(data[0]) for _, data in face_landmark_detector_sample_inputs.items()]) # Compile model on a specific device face_landmark_detector_compile_job = hub.submit_compile_job( model=traced_face_landmark_detector_model , device=device, input_specs=face_landmark_detector_model.get_input_spec(), ) # Get target model to run on-device face_landmark_detector_target_model = face_landmark_detector_compile_job.get_target_model() ``` Step 2: **Performance profiling on cloud-hosted device** After compiling models from step 1. Models can be profiled model on-device using the `target_model`. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics. ```python face_detector_profile_job = hub.submit_profile_job( model=face_detector_target_model, device=device, ) face_landmark_detector_profile_job = hub.submit_profile_job( model=face_landmark_detector_target_model, device=device, ) ``` Step 3: **Verify on-device accuracy** To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device. ```python face_detector_input_data = face_detector_model.sample_inputs() face_detector_inference_job = hub.submit_inference_job( model=face_detector_target_model, device=device, inputs=face_detector_input_data, ) face_detector_inference_job.download_output_data() face_landmark_detector_input_data = face_landmark_detector_model.sample_inputs() face_landmark_detector_inference_job = hub.submit_inference_job( model=face_landmark_detector_target_model, device=device, inputs=face_landmark_detector_input_data, ) face_landmark_detector_inference_job.download_output_data() ``` With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output. **Note**: This on-device profiling and inference requires access to Qualcomm® AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup). ## Deploying compiled model to Android The models can be deployed using multiple runtimes: - TensorFlow Lite (`.tflite` export): [This tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a guide to deploy the .tflite model in an Android application. - QNN (`.so` export ): This [sample app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html) provides instructions on how to use the `.so` shared library in an Android application. ## View on Qualcomm® AI Hub Get more details on MediaPipe-Face-Detection's performance across various devices [here](https://aihub.qualcomm.com/models/mediapipe_face). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of MediaPipe-Face-Detection can be found [here](https://github.com/zmurez/MediaPipePyTorch/blob/master/LICENSE). * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf) ## References * [BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs](https://arxiv.org/abs/1907.05047) * [Source Model Implementation](https://github.com/zmurez/MediaPipePyTorch/) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).